Skip to content

feat: upgrade MiniMax default model to M3#1144

Open
octo-patch wants to merge 1 commit into
dataease:mainfrom
octo-patch:feature/upgrade-minimax-m3
Open

feat: upgrade MiniMax default model to M3#1144
octo-patch wants to merge 1 commit into
dataease:mainfrom
octo-patch:feature/upgrade-minimax-m3

Conversation

@octo-patch
Copy link
Copy Markdown
Contributor

Summary

Upgrade MiniMax model configuration to include the latest M3 model as the new default.

Changes

  • Add MiniMax-M3 to the model selection list (placed first as the new default)
  • Retain MiniMax-M2.7 as an available alternative for backward compatibility
  • Remove deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed from the list
  • Update related unit and integration tests to reflect the new model list

Why

MiniMax-M3 is the new flagship model with 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. Keeping M2.7 ensures users with existing configurations have a smooth migration path while M2.5 variants are no longer recommended.

Testing

  • Unit tests updated and passing (24/24 in tests/test_supplier_config.py)
  • Integration tests updated to use MiniMax-M3 against api.minimax.io

- Add MiniMax-M3 as the new default model
- Retain MiniMax-M2.7 as available alternative
- Remove deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed
- Update unit and integration tests for the new model list
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant